中文
相关论文

相关论文: Properties of Discrete Sliced Wasserstein Losses

200 篇论文

In this paper, we investigate the properties of the Sliced Wasserstein Distance (SW) when employed as an objective functional. The SW metric has gained significant interest in the optimal transport and machine learning literature, due to…

机器学习 · 统计学 2025-08-21 Christophe Vauthier , Anna Korba , Quentin Mérigot

The sliced Wasserstein (SW) distance has been widely recognized as a statistically effective and computationally efficient metric between two probability measures. A key component of the SW distance is the slicing distribution. There are…

机器学习 · 统计学 2024-01-02 Khai Nguyen , Nhat Ho

The sliced Wasserstein metric compares probability measures on $\mathbb{R}^d$ by taking averages of the Wasserstein distances between projections of the measures to lines. The distance has found a range of applications in statistics and…

偏微分方程分析 · 数学 2024-11-25 Sangmin Park , Dejan Slepčev

The Sliced-Wasserstein distance (SW) is being increasingly used in machine learning applications as an alternative to the Wasserstein distance and offers significant computational and statistical benefits. Since it is defined as an…

机器学习 · 统计学 2022-01-05 Kimia Nadjahi , Alain Durmus , Pierre E. Jacob , Roland Badeau , Umut Şimşekli

Sliced-Wasserstein distance (SW) and its variant, Max Sliced-Wasserstein distance (Max-SW), have been used widely in the recent years due to their fast computation and scalability even when the probability measures lie in a very high…

机器学习 · 统计学 2020-10-06 Khai Nguyen , Nhat Ho , Tung Pham , Hung Bui

Optimal Transport has sparked vivid interest in recent years, in particular thanks to the Wasserstein distance, which provides a geometrically sensible and intuitive way of comparing probability measures. For computational reasons, the…

机器学习 · 计算机科学 2024-03-19 Eloi Tanguy

The sliced Wasserstein (SW) distances between two probability measures are defined as the expectation of the Wasserstein distance between two one-dimensional projections of the two measures. The randomness comes from a projecting direction…

机器学习 · 统计学 2024-02-20 Khai Nguyen , Nhat Ho

The Sliced-Wasserstein (SW) distance between probability measures is defined as the average of the Wasserstein distances resulting for the associated one-dimensional projections. As a consequence, the SW distance can be written as an…

机器学习 · 统计学 2024-05-16 Rémi Leluc , Aymeric Dieuleveut , François Portier , Johan Segers , Aigerim Zhuman

Since the introduction of the Sliced Wasserstein distance in the literature, its simplicity and efficiency have made it one of the most interesting surrogate for the Wasserstein distance in image processing and machine learning. However,…

最优化与控制 · 数学 2025-08-05 Eloi Tanguy , Laetitia Chapel , Julie Delon

Sliced Wasserstein (SW) distances offer an efficient method for comparing high-dimensional probability measures by projecting them onto multiple 1-dimensional probability distributions. However, identifying informative slicing directions…

机器学习 · 计算机科学 2025-06-04 Navid NaderiAlizadeh , Darian Salehi , Xinran Liu , Soheil Kolouri

The Sliced-Wasserstein distance (SW) is a computationally efficient and theoretically grounded alternative to the Wasserstein distance. Yet, the literature on its statistical properties -- or, more accurately, its generalization properties…

机器学习 · 统计学 2023-06-01 Ruben Ohana , Kimia Nadjahi , Alain Rakotomamonjy , Liva Ralaivola

Many variants of the Wasserstein distance have been introduced to reduce its original computational burden. In particular the Sliced-Wasserstein distance (SW), which leverages one-dimensional projections for which a closed-form solution of…

机器学习 · 统计学 2023-01-31 Clément Bonet , Paul Berg , Nicolas Courty , François Septier , Lucas Drumetz , Minh-Tan Pham

Minimum expected distance estimation (MEDE) algorithms have been widely used for probabilistic models with intractable likelihood functions and they have become increasingly popular due to their use in implicit generative modeling (e.g.…

机器学习 · 统计学 2020-03-25 Kimia Nadjahi , Alain Durmus , Umut Şimşekli , Roland Badeau

Recently used in various machine learning contexts, the Gromov-Wasserstein distance (GW) allows for comparing distributions whose supports do not necessarily lie in the same metric space. However, this Optimal Transport (OT) distance…

机器学习 · 统计学 2022-10-21 Titouan Vayer , Rémi Flamary , Romain Tavenard , Laetitia Chapel , Nicolas Courty

The Wasserstein distance and its variations, e.g., the sliced-Wasserstein (SW) distance, have recently drawn attention from the machine learning community. The SW distance, specifically, was shown to have similar properties to the…

机器学习 · 计算机科学 2019-02-04 Soheil Kolouri , Kimia Nadjahi , Umut Simsekli , Roland Badeau , Gustavo K. Rohde

Sliced Wasserstein distances preserve properties of classic Wasserstein distances while being more scalable for computation and estimation in high dimensions. The goal of this work is to quantify this scalability from three key aspects: (i)…

机器学习 · 统计学 2022-10-18 Sloan Nietert , Ritwik Sadhu , Ziv Goldfeld , Kengo Kato

Spherical Sliced-Wasserstein (SSW) has recently been proposed to measure the discrepancy between spherical data distributions in various fields, such as geology, medical domains, computer vision, and deep representation learning. However,…

机器学习 · 计算机科学 2024-12-30 Hongliang Zhang , Shuo Chen , Lei Luo , Jian Yang

Wasserstein distances define a metric between probability measures on arbitrary metric spaces, including meta-measures (measures over measures). The resulting Wasserstein over Wasserstein (WoW) distance is a powerful, but computationally…

机器学习 · 计算机科学 2026-02-20 Moritz Piening , Robert Beinert

Developing machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts. Among the numerous ways to address privacy-preserving learning, we here take the perspective of computing the…

机器学习 · 计算机科学 2021-07-06 Alain Rakotomamonjy , Liva Ralaivola

Gromov--Wasserstein (GW) distances compare graphs, shapes, and point clouds through internal distances, without requiring a common coordinate system. This invariance is powerful, but discrete GW is a nonconvex quadratic optimal transport…

机器学习 · 计算机科学 2026-05-15 Ao Xu , Tieru Wu
‹ 上一页 1 2 3 10 下一页 ›